INDEX

Explanations

historical references and significant events

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.16

Fil

-0.15

uez

-0.15

 rigor

-0.15

 Bench

-0.15

Ð¾

-0.14

æīĢ

-0.14

 maxim

-0.14

 ikke

-0.14

TS

-0.14

POSITIVE LOGITS

Ã¸d

0.18

cala

0.17

PPER

0.16

koli

0.16

icros

0.15

 eskort

0.15

icolor

0.15

ãĤīãģĦ

0.15

ãĥ¼ãĥŃ

0.15

annonce

0.14

Activations Density 0.064%

historical references and significant events

No Comments

No Known Activations

historical references and significant events

No Comments

No Known Activations